business <- read_csv("./data/business.csv") %>% 
  mutate(name = str_sub(name, 2, -2)) %>% 
  mutate(address = str_sub(address, 2, -2)) %>% 
  filter(neighborhood != "Downtown Tampa" & neighborhood != "North Valley")

categories <- business %>% 
  select(business_id, categories) %>% 
  separate(categories, into = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "cat8", "cat9", "cat10", "cat11", "cat12", "cat13", "cat14", "cat15", "cat16", "cat17", "cat18", "cat19", "cat20", "cat21", "cat22", "cat23", "cat24", "cat25"), sep  = ";") %>% 
  gather(key = "cat_id", value = "category", starts_with("cat")) %>% 
  select(-cat_id) 
  
restaurant_ids <- categories %>% 
  filter(category == "Restaurants") %>% 
  distinct(business_id)

restaurants <- business %>% 
  mutate(is_rest = ifelse(str_detect(categories, ";Restaurant") == TRUE, 1, 
                                ifelse(str_match(categories, ";Food") == TRUE, 1, 0))) %>% 
  filter(is_rest == 1) %>% 
  select(-is_rest) 

attributes <- read_csv("./data/attributes.csv") %>% 
  janitor::clean_names() %>% 
  select(business_id, alcohol)

restaurants <- restaurants %>% 
  left_join(attributes, by = "business_id")

restaurants %>% 
  group_by(neighborhood) %>% 
  count() %>% 
  arrange(n) %>% 
  knitr::kable()

restaurants %>% 
select(business_id, neighborhood, stars) %>% 
  distinct() %>% 
  group_by(neighborhood, stars) %>% 
  tally %>% 
  rename(my_count = n) %>% 
  spread(key = stars, value = my_count) %>% 
  knitr::kable()

restaurants %>%
  mutate(review_count = as.numeric(review_count)) %>% 
  select(business_id, neighborhood, review_count) %>% 
  group_by(neighborhood) %>% 
  summarise(Average_Number_of_Reviews = mean(review_count)) %>% 
  knitr::kable()

restaurants %>% 
  group_by(neighborhood) %>% 
  summarize(avg = mean(stars), sd = sd(stars)) %>% 
  arrange(avg) %>% 
  knitr::kable()